Matches in SemOpenAlex for { <https://semopenalex.org/work/W2238307037> ?p ?o ?g. }
- W2238307037 endingPage "28" @default.
- W2238307037 startingPage "1" @default.
- W2238307037 abstract "Modern SoCs integrate multiple CPU cores and hardware accelerators (HWAs) that share the same main memory system, causing interference among memory requests from different agents. The result of this interference, if it is not controlled well, is missed deadlines for HWAs and low CPU performance. Few previous works have tackled this problem. State-of-the-art mechanisms designed for CPU-GPU systems strive to meet a target frame rate for GPUs by prioritizing the GPU close to the time when it has to complete a frame. We observe two major problems when such an approach is adapted to a heterogeneous CPU-HWA system. First, HWAs miss deadlines because they are prioritized only when close to their deadlines. Second, such an approach does not consider the diverse memory access characteristics of different applications running on CPUs and HWAs, leading to low performance for latency-sensitive CPU applications and deadline misses for some HWAs, including GPUs. In this article, we propose a Deadline-Aware memory Scheduler for Heterogeneous systems (DASH), which overcomes these problems using three key ideas, with the goal of meeting HWAs’ deadlines while providing high CPU performance. First, DASH prioritizes an HWA when it is not on track to meet its deadline any time during a deadline period, instead of prioritizing it only when close to a deadline. Second, DASH prioritizes HWAs over memory-intensive CPU applications based on the observation that memory-intensive applications’ performance is not sensitive to memory latency. Third, DASH treats short-deadline HWAs differently as they are more likely to miss their deadlines and schedules their requests based on worst-case memory access time estimates. Extensive evaluations across a wide variety of different workloads and systems show that DASH achieves significantly better CPU performance than the best previous scheduler while always meeting the deadlines for all HWAs, including GPUs, thereby largely improving frame rates." @default.
- W2238307037 created "2016-06-24" @default.
- W2238307037 creator A5013984674 @default.
- W2238307037 creator A5050695684 @default.
- W2238307037 creator A5064619088 @default.
- W2238307037 creator A5081021239 @default.
- W2238307037 date "2016-01-04" @default.
- W2238307037 modified "2023-10-17" @default.
- W2238307037 title "DASH" @default.
- W2238307037 cites W1964858680 @default.
- W2238307037 cites W1973980980 @default.
- W2238307037 cites W1974967412 @default.
- W2238307037 cites W1977149250 @default.
- W2238307037 cites W1979866689 @default.
- W2238307037 cites W1980927950 @default.
- W2238307037 cites W1980997960 @default.
- W2238307037 cites W1981588964 @default.
- W2238307037 cites W1992487929 @default.
- W2238307037 cites W1993488239 @default.
- W2238307037 cites W2000730311 @default.
- W2238307037 cites W2008251984 @default.
- W2238307037 cites W2014453461 @default.
- W2238307037 cites W2018814245 @default.
- W2238307037 cites W2064039391 @default.
- W2238307037 cites W2064344201 @default.
- W2238307037 cites W2079248286 @default.
- W2238307037 cites W2098040113 @default.
- W2238307037 cites W2102800454 @default.
- W2238307037 cites W2102871765 @default.
- W2238307037 cites W2113222460 @default.
- W2238307037 cites W2115172404 @default.
- W2238307037 cites W2116826559 @default.
- W2238307037 cites W2119605622 @default.
- W2238307037 cites W2120945246 @default.
- W2238307037 cites W2121256363 @default.
- W2238307037 cites W2122510369 @default.
- W2238307037 cites W2124237318 @default.
- W2238307037 cites W2126570805 @default.
- W2238307037 cites W2127760637 @default.
- W2238307037 cites W2129381159 @default.
- W2238307037 cites W2136684653 @default.
- W2238307037 cites W2142875853 @default.
- W2238307037 cites W2144077857 @default.
- W2238307037 cites W2145451976 @default.
- W2238307037 cites W2145988169 @default.
- W2238307037 cites W2146398836 @default.
- W2238307037 cites W2149075075 @default.
- W2238307037 cites W2150196852 @default.
- W2238307037 cites W2150380088 @default.
- W2238307037 cites W2152724437 @default.
- W2238307037 cites W2153882937 @default.
- W2238307037 cites W2158620667 @default.
- W2238307037 cites W2159908132 @default.
- W2238307037 cites W2162293132 @default.
- W2238307037 cites W2165284728 @default.
- W2238307037 cites W2165683591 @default.
- W2238307037 cites W2166697045 @default.
- W2238307037 cites W2170257519 @default.
- W2238307037 cites W2233523872 @default.
- W2238307037 cites W2234128234 @default.
- W2238307037 cites W2999623539 @default.
- W2238307037 cites W3100461726 @default.
- W2238307037 cites W3145545382 @default.
- W2238307037 cites W3147501999 @default.
- W2238307037 cites W3147974890 @default.
- W2238307037 cites W4210790398 @default.
- W2238307037 cites W4236382111 @default.
- W2238307037 cites W4238816702 @default.
- W2238307037 cites W4239813889 @default.
- W2238307037 cites W4245436356 @default.
- W2238307037 cites W4251430913 @default.
- W2238307037 doi "https://doi.org/10.1145/2847255" @default.
- W2238307037 hasPublicationYear "2016" @default.
- W2238307037 type Work @default.
- W2238307037 sameAs 2238307037 @default.
- W2238307037 citedByCount "93" @default.
- W2238307037 countsByYear W22383070372016 @default.
- W2238307037 countsByYear W22383070372017 @default.
- W2238307037 countsByYear W22383070372018 @default.
- W2238307037 countsByYear W22383070372019 @default.
- W2238307037 countsByYear W22383070372020 @default.
- W2238307037 countsByYear W22383070372021 @default.
- W2238307037 countsByYear W22383070372022 @default.
- W2238307037 countsByYear W22383070372023 @default.
- W2238307037 crossrefType "journal-article" @default.
- W2238307037 hasAuthorship W2238307037A5013984674 @default.
- W2238307037 hasAuthorship W2238307037A5050695684 @default.
- W2238307037 hasAuthorship W2238307037A5064619088 @default.
- W2238307037 hasAuthorship W2238307037A5081021239 @default.
- W2238307037 hasBestOaLocation W22383070371 @default.
- W2238307037 hasConcept C100800780 @default.
- W2238307037 hasConcept C111919701 @default.
- W2238307037 hasConcept C126042441 @default.
- W2238307037 hasConcept C149635348 @default.
- W2238307037 hasConcept C173608175 @default.
- W2238307037 hasConcept C189930140 @default.
- W2238307037 hasConcept C26517878 @default.
- W2238307037 hasConcept C2776090536 @default.